agent-host-logs

Analysieren Sie Agent Host-Debug-Log-Exporte. Verwenden Sie, wenn ein ah-logs- oder ahp-logs-Zip/Ordner, ein Export Agent Host Debug Logs-Bundle, events.jsonl, AHP JSONL… bereitgestellt wird.

npx skills add https://github.com/microsoft/vscode --skill agent-host-logs

Agent Host Debug Logs

Use this skill to orient to bundles produced by Developer: Export Agent Host Debug Logs.... These are different from the normal timestamped Code OSS log directory.

Treat the bundle as sensitive: it can contain tokens, prompts, file contents, terminal output, paths, and settings. Keep analysis local and avoid quoting secrets or unrelated user content. Timestamps, event names, IDs, status values, and general property values are fine.

Open the Bundle

The export name usually starts with ah-logs and may be a zip or an already-unpacked folder. For a zip, use the bundled extractor:

python3 .github/skills/agent-host-logs/scripts/extract.py "<archive>.zip"

The final line gives the temporary extraction path. Work from that folder and delete only that exact folder when finished.

Files are collected best-effort, so a valid bundle may contain only some of these:

events.jsonl
usage.jsonl
customizations.json
agenthost.log
agenthost.1.log
agenthost-server.log
vscode-logs/Window/renderer.log
vscode-logs/Window/renderer.1.log
vscode-logs/Shared/sharedprocess.log
ahp/*.jsonl
copilot-logs/*.log
remote-agenthost.log

What the Files Mean

The basic flow is:

Window/client <-> AHP <-> Agent Host process <-> Copilot SDK
PathWhat it shows
events.jsonlPersisted Copilot SDK events for the selected session: turns, messages, tools, permissions, hooks, skills, and subagents. It can cover a much longer period than the other logs.
usage.jsonlClient-captured token/credit usage, one record per model call (turnId, model, input/output/cache tokens, cumulative totalNanoAiu). The SDK's assistant.usage event is ephemeral and never reaches events.jsonl, so this is the only per-call usage record. Present only when agent-host debug logging was on.
customizations.jsonSnapshot of the skills/hooks/agents/MCP servers loaded for the session. The SDK's session.*_loaded events are ephemeral, so this is the only record of what was actually active. Present only when agent-host debug logging was on.
ahp/*.jsonlAHP traffic for a client connection. _ahpLog.dir is c2s or s2c; _ahpLog.ts is the wire timestamp. Use this to see requests, responses, subscriptions, actions, notifications, and client-visible ordering.
agenthost*.logLocal or server Agent Host process behavior: startup, auth, sessions, provider events, tools, Git/worktrees, and host-side errors. Numbered files are older rotated segments.
copilot-logs/*.logCopilot SDK process logs that mention the selected session ID. A process log may contain other sessions too.
vscode-logs/Window/*Current and rotated files from the Window log group, including renderer/client behavior, network activity, views, and other window-owned logs.
vscode-logs/Shared/*Current and rotated files from the Shared log group. Usually secondary evidence and often noisy.
Agent Host (<name>).logForwarded logs from a named remote Agent Host.
remote-agenthost.logA directly downloaded remote agenthost.log, when available.

How to Start

  1. List the files and note their sizes.
  2. Identify the reported symptom, approximate time, local or remote host, and any known session, chat, turn, request, or tool ID.
  3. Start with the file closest to the symptom:
    • Turn or provider behavior: events.jsonl
    • Token/credit usage or cost questions: usage.jsonl
    • Client/server state or ordering: ahp/*.jsonl
    • Host implementation failure: agenthost*.log
    • SDK behavior: copilot-logs/*.log
    • UI behavior: vscode-logs/Window/renderer.log and its rotated segments
  4. Search by the known time or ID, then follow the same operation into the adjacent layer.

Useful correlation fields include the raw session ID, session/chat URI, turnId, interactionId, tool/request IDs, JSON-RPC request id, AHP serverSeq, and event id/parentId.

Copilot Session Refresh Failures

At the default Info log level, agenthost*.log records the refresh operation, configuration and SDK session IDs, chat, turn, and first matching reason. Only the first matching trigger is reported, preserving the restart checks' short-circuit order. Structural reasons distinguish client tools, client plugins, and root MCP configuration without logging their contents.

Follow Preparing SDK session and the paired SDK resumeSession started / settled records by attemptId. Follow each attached SDK session's shutdown and disconnect records by instanceId, which distinguishes successive wrappers of the same SDK session. A disconnect wait completed record with disconnectRpc=pending and shutdownReceived=true means the shutdown notification unblocked the caller before the disconnect RPC settled. A later RPC completion or failure, including after disposed=true, is logged separately. Neither the notification nor the host-side wait alone proves that native cleanup finished; correlate these with the SDK process log before concluding there was a teardown/resume race.

Important Tips

  • events.jsonl, Copilot SDK logs, and AHP timestamps are normally UTC. The plain .log files may use local machine time; remote logs may use another timezone.
  • An AHP log is connection-scoped and can contain multiple sessions. A Copilot SDK process log can also contain multiple sessions.
  • AHP files rotate as .jsonl, .1.jsonl, .2.jsonl, and so on. Use _ahpLog.ts to reconstruct order.
  • A subscribe result can contain a full snapshot; its contents did not necessarily change at subscription time.
  • _ahpLog.truncated: true means large values were omitted from that log record.
  • Warning or error severity alone does not prove causality. Look for the matching failed response, missing completion, or user-visible consequence.
  • Missing files are normal because export collection is best-effort.

Mehr Skills von microsoft

oss-growth
microsoft
OSS-Wachstums-Hacker-Persona
agent-framework-azure-ai-py
microsoft
Erstellen Sie Azure AI Foundry-Agents mit dem Microsoft Agent Framework Python SDK (agent-framework-azure-ai). Verwenden Sie dies beim Erstellen persistenter Agents mit AzureAIAgentsProvider, bei der Nutzung gehosteter Tools (Code-Interpreter, Dateisuche, Websuche), bei der Integration von MCP-Servern, bei der Verwaltung von Konversationsthreads oder bei der Implementierung von Streaming-Antworten. Umfasst Funktionstools, strukturierte Ausgaben und Multi-Tool-Agents.
development
airunway-aks-setup
microsoft
Richte AI Runway auf AKS ein – vom leeren Cluster bis zum laufenden Modell. Umfasst Cluster-Überprüfung, Controller-Installation, GPU-Bewertung, Provider-Einrichtung und erste Bereitstellung. WANN: „AI Runway einrichten“, „AKS-Cluster onboarden“, „AI Runway installieren“, „airunway setup“, „Modell auf AKS bereitstellen“, „GPU-Inferenz auf AKS“, „KAITO-Setup auf AKS“, „LLM auf AKS ausführen“, „vLLM auf AKS“, „Modell-Serving auf AKS einrichten“, „AI Runway-Controller“.
devops
appinsights-instrumentation
microsoft
Leitfaden zur Instrumentierung von Webanwendungen mit Azure Application Insights. Bietet Telemetriemuster, SDK-Einrichtung und Konfigurationsreferenzen. WANN: wie man eine App instrumentiert, App Insights SDK, Telemetriemuster, was ist App Insights, Application Insights-Anleitung, Instrumentierungsbeispiele, APM-Best Practices.
devops
applicationinsights-web-ts
microsoft
Instrumentieren Sie Browser-/Web-Apps mit dem Application Insights JavaScript SDK (@microsoft/applicationinsights-web). Verwenden Sie es für Real User Monitoring (RUM) – Seitenaufrufe, Klicks, AJAX/Fetch-Abhängigkeiten, Ausnahmen, benutzerdefinierte Ereignisse und browser-seitige GenAI-Agent-Traces, die mit Backend-OpenTelemetry-Traces korreliert werden. Umfasst SDK-Loader-Skript und npm-Setup, Framework-Erweiterungen (React, React Native, Angular), Click Analytics, Telemetrie-Initialisierer und OTel-GenAI-Semantik-Konventionen für Agent-/Tool-/Modell-Spans, die vom Browser ausgegeben werden.
devops
azure-ai-anomalydetector-java
microsoft
Erstellen Sie Anomalieerkennungsanwendungen mit dem Azure AI Anomaly Detector SDK für Java. Verwenden Sie dies bei der Implementierung von univariater/multivariater Anomalieerkennung, Zeitreihenanalyse oder KI-gestützter Überwachung.
development
azure-ai-language-conversations-py
microsoft
Implementieren Sie Conversational Language Understanding (CLU) mit dem azure-ai-language-conversations Python SDK. Verwenden Sie dies, wenn Sie mit ConversationAnalysisClient arbeiten, um Gesprächsabsichten und Entitäten zu analysieren, NLP-Funktionen zu erstellen oder Sprachverständnis in Anwendungen zu integrieren.
development
azure-ai-ml-py
microsoft
Azure Machine Learning SDK v2 für Python. Verwenden für ML-Workspaces, Jobs, Modelle, Datensätze, Compute und Pipelines. Auslöser: „azure-ai-ml“, „MLClient“, „Workspace“, „Modell-Registry“, „Trainings-Jobs“, „Datensätze“.
development